公开(公告)号：US20240220812A1

公开(公告)日：2024-07-04

申请号：US17474950

申请日：2021-09-14

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Ruiqing ZHANG ,  Xiyang WANG ,  Zhongjun HE ,  Zhi LI ,  Hua WU

IPC: G06N3/094

CPC classification number: G06N3/094

Abstract: A method for training a machine translation (MT) model and an electronic device are provided. The technical solution includes: obtaining an original training sample configured to train an MT model; generating at least one adversarial training sample of the MT model based on the original training sample; training the MT model based on the original training sample and the adversarial training sample.

公开(公告)号：US20230342560A1

公开(公告)日：2023-10-26

申请号：US18121351

申请日：2023-03-14

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Ruiqing ZHANG ,  Hui LIU ,  Xiyang WANG ,  Zhongjun HE ,  Zhi LI ,  Hua WU

IPC: G06F40/47 ,  G06F40/166 ,  G06F40/30

CPC classification number: G06F40/47 ,  G06F40/166 ,  G06F40/30 ,  G06F40/247

Abstract: A text translation method is described that includes initially acquiring text. Thereafter, first text is determined in the initial text; and second text is determined according to the first text, where the second text is used for describing the first text. Additionally, initial text is translated to obtain initial translation text, and the second text is translated to obtain description translation text. Thereafter, the initial translation text is updated according to the description translation text to obtain target translation text of the initial text.